Method and system for the identification of compounds in complex biological or environmental samples by receiving (102) a mass spectrum (1) from a mass spectrometry coupled with a separation technique; for each data point (2) of the mass spectrum (1), annotating (106) in an annotation database (12) combinations of formulas and adducts the theoretical mass-to-charge ratio of which (m/z).sup.T corresponds to the mass-to-charge ratio (m/z) measured of the data point (2); for each formula and adduct annotated, detecting (108) regions of interest in a retention time range (RT.sub.0-RT.sub.1) according to characterisation criteria; generating (110) an inclusion list (14) with the retention time ranges (RT.sub.0-RT.sub.1) and the theoretical mass-to-charge ratios (m/z).sup.T of the formulas and adducts associated with the regions of interest; and sending (112) the inclusion list to a mass spectrometer for the identification of compounds in the sample by tandem mass spectrometry.

Method and system for the identification of compounds in complex biological or environmental samples by receiving (102) a mass spectrum (1) from a mass spectrometry coupled with a separation technique; for each data point (2) of the mass spectrum (1), annotating (106) in an annotation database (12) combinations of formulas and adducts the theoretical mass-to-charge ratio of which (m/z).sup.T corresponds to the mass-to-charge ratio (m/z) measured of the data point (2); for each formula and adduct annotated, detecting (108) regions of interest in a retention time range (RT.sub.0-RT.sub.1) according to characterisation criteria; generating (110) an inclusion list (14) with the retention time ranges (RT.sub.0-RT.sub.1) and the theoretical mass-to-charge ratios (m/z).sup.T of the formulas and adducts associated with the regions of interest; and sending (112) the inclusion list to a mass spectrometer for the identification of compounds in the sample by tandem mass spectrometry.

A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

Techniques are disclosed for using a genetic algorithm to identify a processing pipeline that transforms spectra into a form usable to generate predicted characteristics of corresponding samples. The genetic algorithm is used to generate and evaluate multiple candidate solutions specifying various pre-processing and machine-learning-processing configurations. The processing pipeline is defined based on the candidate solutions.

Provided are a first measurement apparatus that measures the stable isotope ratios of a carbon element and a hydrogen element contained in hair of animal, and a verification device having a database including first reference data for the stable isotope ratios of the carbon element and the hydrogen element, which are classified for each production area of the hair of the animal, in which the first measurement apparatus measures the stable isotope ratios of the carbon element and the hydrogen element contained in the hair of the animal to be measured, and the verification device compares the measurement result of the first measurement apparatus with the first reference data, and determines the production area of the hair of the animal to be measured based on the comparison result.

Provided are a first measurement apparatus that measures the stable isotope ratios of a carbon element and a hydrogen element contained in hair of animal, and a verification device having a database including first reference data for the stable isotope ratios of the carbon element and the hydrogen element, which are classified for each production area of the hair of the animal, in which the first measurement apparatus measures the stable isotope ratios of the carbon element and the hydrogen element contained in the hair of the animal to be measured, and the verification device compares the measurement result of the first measurement apparatus with the first reference data, and determines the production area of the hair of the animal to be measured based on the comparison result.

A method of identifying molecular parameters in a complex mixture may include receiving a set of combined transition frequencies and analyzing the set of combined transition frequencies using a first trained artificial neural network to generate a plurality of separated transition frequency sets. Each of the plurality of separated frequency sets may be analyzed using a second trained artificial neural network to generate a respective set of estimated spectral parameters. The method may include identifying a set of molecular parameters corresponding to the set of separated transition frequencies.

A method of identifying molecular parameters in a complex mixture may include receiving a set of combined transition frequencies and analyzing the set of combined transition frequencies using a first trained artificial neural network to generate a plurality of separated transition frequency sets. Each of the plurality of separated frequency sets may be analyzed using a second trained artificial neural network to generate a respective set of estimated spectral parameters. The method may include identifying a set of molecular parameters corresponding to the set of separated transition frequencies.

A chemical pattern recognition method for evaluating the quality of a traditional Chinese medicine based on medicine effect information, comprising: collecting chemical information of a traditional Chinese medicine sample, obtaining medicine effect information reflecting a clinical therapeutic effect thereof, performing spectrum-effect relationship analysis on the chemical information and the medicine effect information, and obtaining an index significantly related to the medicine effect as a feature chemical index; dividing the traditional Chinese medicine sample into a training set and a test set; using a pattern recognition method to extract a feature variable from samples of the training set by taking the feature chemical index as an input variable; building a pattern recognition model using the feature variable; and substituting feature variable values of samples of the test set into the model, and completing chemical pattern recognition evaluation of the quality of the traditional Chinese medicine. According to the method, chemical reference substances are not needed, the chemical pattern recognition model is built on the basis of the feature chemical index reflecting the medicine effect, the one-sidedness and the subjectivity of the existing standards are overcome, and a traditional Chinese medicine quality evaluation system capable of reflecting both the clinical therapeutic effect and overall chemical composition information is finally formed.